同步wx公众号(arXiv每日论文速递),支持后台回复'search 关键词'查询相关的最新论文。有些许帮助的话,麻烦关注一下哦(* ̄rǒ ̄)
cs.CV 方向,今日共计63篇
[检测分类相关]:
【1】 Revisiting Feature Alignment for One-stage Object Detection
一步目标检测中的特征对齐方法
作者: Yuntao Chen, Zhaoxiang Zhang
链接:https://arxiv.org/abs/1908.01570
【2】 Automated Detection System for Adversarial Examples with High-Frequency Noises Sieve
高频噪声筛分对抗实例自动检测系统
作者: Dang Duy Thang, Toshihiro Matsui
备注:Appear to 11th International Symposium on Cyberspace Safety and Security CSS 2019, Guangzhou, China
链接:https://arxiv.org/abs/1908.01469
【3】 ARGAN: Attentive Recurrent Generative Adversarial Network for Shadow Detection and Removal
ARGAN:用于阴影检测和去除的注意循环生成对抗网络
作者: Bin Ding, Chunxia Xiao
备注:The paper was accepted to the IEEE / CVF International Conference on Computer Vision (ICCV) 2019
链接:https://arxiv.org/abs/1908.01323
【4】 Low-Rank Pairwise Alignment Bilinear Network For Few-Shot Fine-Grained Image Classification
低秩成对双线性网络在少镜头细粒度图像分类中的应用
作者: Huaxi Huang, Qiang Wu
链接:https://arxiv.org/abs/1908.01313
【5】 Simultaneous Semantic Segmentation and Outlier Detection in Presence of Domain Shift
存在域移的同时语义分割和离群点检测
作者: Petra Bevandić, Siniša Šegvić
备注:Accepted to German Conference on Pattern Recognition 2019. 25 pages, 10 figures, 9 tables
链接:https://arxiv.org/abs/1908.01098
[分割/语义相关]:
【1】 SqueezeNAS: Fast neural architecture search for faster semantic segmentation
SqueezeNAS:快速神经架构搜索,用于更快的语义分割
作者: Albert Shaw, Sammy Sidhu
链接:https://arxiv.org/abs/1908.01748
【2】 Part Segmentation for Highly Accurate Deformable Tracking in Occlusions via Fully Convolutional Neural Networks
基于完全卷积神经网络的高精度可变形遮挡跟踪零件分割
作者: Weilin Wan, Dieter Fox
链接:https://arxiv.org/abs/1908.01504
【3】 Deep Neural Network for Semantic-based Text Recognition in Images
用于图像中基于语义的文本识别的深度神经网络
作者: Yi Zheng, Margrit Betke
链接:https://arxiv.org/abs/1908.01403
【4】 Knee menisci segmentation and relaxometry of 3D ultrashort echo time (UTE) cones MR imaging using attention U-Net with transfer learning
膝关节半月板分割和松弛测量3D超短回波时间(UTE)锥体MR成像使用转移学习的注意U-net
作者: Michal Byra, Jiang Du
链接:https://arxiv.org/abs/1908.01594
【5】 Unsupervised Microvascular Image Segmentation Using an Active Contours Mimicking Neural Network
一种模拟神经网络的活动轮廓无监督微血管图像分割方法
作者: Shir Gur, Pablo Blinder
链接:https://arxiv.org/abs/1908.01373
【6】 Automatic segmentation of kidney and liver tumors in CT images
CT图像中肾脏和肝脏肿瘤的自动分割
作者: Dina B. Efremova, Peter Haddawy
备注:Method description manuscript for our test predictions for the 2019 Kidney Tumor Segmentation Challenge, this https URL
链接:https://arxiv.org/abs/1908.01279
[GAN/对抗式/生成式相关]:
【1】 Adversarial Self-Defense for Cycle-Consistent GANs
循环一致GAN的对抗性自卫
作者: Dina Bashkirova, Kate Saenko
链接:https://arxiv.org/abs/1908.01517
【2】 Adversarial View-Consistent Learning for Monocular Depth Estimation
用于单目深度估计的对抗性视图一致学习
作者: Yixuan Liu, Shengjin Wang
备注:BMVC 2019 Spotlight
链接:https://arxiv.org/abs/1908.01301
【3】 Cycle In Cycle Generative Adversarial Networks for Keypoint-Guided Image Generation
用于关键点引导的图像生成的循环中循环生成对抗性网络
作者: Hao Tang, Yan Yan
备注:9 pages, 8 figures, accepted to ACM MM 2019
链接:https://arxiv.org/abs/1908.00999
【4】 A principled approach for generating adversarial images under non-smooth dissimilarity metrics
一种在非光滑相异度度量下生成对抗性图像的原则性方法
作者: Aram-Alexandre Pooladian, Adam Oberman
链接:https://arxiv.org/abs/1908.01667
[图像/视频检索]:
【1】 A Fast Content-Based Image Retrieval Method Using Deep Visual Features
一种利用深度视觉特征的快速基于内容的图像检索方法
作者: Hiroki Tanioka
备注:accepted in ICDAR-WML: The 2nd International Workshop on Machine Learning 2019
链接:https://arxiv.org/abs/1908.01505
[行为/时空/光流/姿态/运动]:
【1】 Learning Local Feature Descriptor with Motion Attribute for Vision-based Localization
基于视觉定位的带有运动属性的局部特征描述子的学习
作者: Yafei Song, Mingyang Li
链接:https://arxiv.org/abs/1908.01180
【2】 Discriminating Spatial and Temporal Relevance in Deep Taylor Decompositions for Explainable Activity Recognition
用于可解释活动识别的Deep Taylor分解中的时空相关性判别
作者: Liam Hiley, David Marshall
备注:5 pages, 2 figures, published at IJCAI19 ExAI workshop
链接:https://arxiv.org/abs/1908.01536
[半/弱/无监督相关]:
【1】 SESF-Fuse: An Unsupervised Deep Model for Multi-Focus Image Fusion
SESF-FUSE:一种用于多聚焦图像融合的无监督深度模型
作者: Boyuan Ma, Yu Zhu
链接:https://arxiv.org/abs/1908.01703
【2】 Unsupervised Learning of Depth and Deep Representation for Visual Odometry from Monocular Videos in a Metric Space
度量空间中单目视频的深度无监督学习和视觉里程计的深度表示
作者: Xiaochuan Yin, Chengju Liu
链接:https://arxiv.org/abs/1908.01367
【3】 ADN: Artifact Disentanglement Network for Unsupervised Metal Artifact Reduction
ADN:用于无监督金属伪影减少的伪影解缠网络
作者: Haofu Liao, Jiebo Luo
备注:This is the extended version of arXiv:1906.01806. This paper is accepted to IEEE Transactions on Medical Imaging
链接:https://arxiv.org/abs/1908.01104
[跟踪相关]:
【1】 Model Decay in Long-Term Tracking
长期跟踪中的模型衰减
作者: Efstratios Gavves, Arnold W. M. Smeulders
链接:https://arxiv.org/abs/1908.01603
【2】 Learning Compact Target-Oriented Feature Representations for Visual Tracking
用于视觉跟踪的学习紧凑的面向目标的特征表示
作者: Chenglong Li, Liang Lin
链接:https://arxiv.org/abs/1908.01442
[迁移学习/domain/主动学习相关]:
【1】 Image to Video Domain Adaptation Using Web Supervision
使用Web监督的图像到视频域自适应
作者: Andrew Kae, Yale Song
链接:https://arxiv.org/abs/1908.01449
[裁剪/量化/加速相关]:
【1】 GDRQ: Group-based Distribution Reshaping for Quantization
GDRQ:用于量化的基于组的分布整形
作者: Haibao Yu, Jianping Shi
链接:https://arxiv.org/abs/1908.01477
【2】 Review of Algorithms for Compressive Sensing of Images
图像压缩感知算法综述
作者: Yoni Sher
链接:https://arxiv.org/abs/1908.01642
【3】 BCD-Net for Low-dose CT Reconstruction: Acceleration, Convergence, and Generalization
用于低剂量CT重建的BCD-net:加速、收敛和泛化
作者: Il Yong Chun, Jeffrey A. Fessler
备注:Accepted to MICCAI 2019, and the authors indicated by asterisks (*) equally contributed to this work
链接:https://arxiv.org/abs/1908.01287
[Re-id相关]:
【1】 Spatially and Temporally Efficient Non-local Attention Network for Video-based Person Re-Identification
时空高效的非局部注意网络用于基于视频的人再识别
作者: Chih-Ting Liu, Shao-Yi Chien
备注:This paper was accepted by 2019 British Machine Vision Conference (BMVC)
链接:https://arxiv.org/abs/1908.01683
【2】 ABD-Net: Attentive but Diverse Person Re-Identification
ABD-NET:关注而多元的人重新识别
作者: Tianlong Chen, Zhangyang Wang
链接:https://arxiv.org/abs/1908.01114
[数据集dataset]:
【1】 Kannada-MNIST: A new handwritten digits dataset for the Kannada language
Kannada-MNIST:用于Kannada语言的新的手写数字数据集
作者: Vinay Uday Prabhu
链接:https://arxiv.org/abs/1908.01242
【2】 Simultaneous Clustering and Optimization for Evolving Datasets
进化数据集的同时聚类和优化
作者: Yawei Zhao, Jianping Yin
链接:https://arxiv.org/abs/1908.01384
[其他视频相关]:
【1】 Fully Automatic Video Colorization with Self-Regularization and Diversity
具有自规则化和分集的全自动视频着色
作者: Chenyang Lei, Qifeng Chen
备注:Published at the Computer Vision and Pattern Recognition (CVPR), 2019
链接:https://arxiv.org/abs/1908.01311
【2】 Searching for Ambiguous Objects in Videos using Relational Referring Expressions
使用关系指代表达式搜索视频中的歧义对象
作者: Hazan Anayurt, Sinan Kalkan
备注:BMVC 2019 camera ready
链接:https://arxiv.org/abs/1908.01189
[其他]:
【1】 Visual-Relation Conscious Image Generation from Structured-Text
基于结构化文本的视觉关系意识图像生成
作者: Duc Minh Vo, Akihiro Sugimoto
链接:https://arxiv.org/abs/1908.01741
【2】 Learning a Unified Embedding for Visual Search at Pinterest
在Pinterest学习视觉搜索的统一嵌入
作者: Andrew Zhai, Charles Rosenberg
备注:in Proceedings of the 25th ACM SIGKDD International Conference on Knowledge and Discovery and Data Mining, 2019
链接:https://arxiv.org/abs/1908.01707
【3】 3D Reconstruction of Deformable Revolving Object under Heavy Hand Interaction
重手交互作用下可变形旋转物体的三维重建
作者: Raoul de Charette, Sotiris Manitsaris
链接:https://arxiv.org/abs/1908.01523
【4】 Pixel2Mesh++: Multi-View 3D Mesh Generation via Deformation
Pixel2Mesh+:通过变形生成多视图3D网格
作者: Chao Wen, Yanwei Fu
备注:Accepted by ICCV 2019
链接:https://arxiv.org/abs/1908.01491
【5】 Walking with MIND: Mental Imagery eNhanceD Embodied QA
心智漫步:心智意象增强的体验式QA
作者: Juncheng Li, Yueting Zhuang
链接:https://arxiv.org/abs/1908.01482
【6】 TopoTag: A Robust and Scalable Topological Fiducial Marker System
TopoTag:一种健壮且可扩展的拓扑基准标记系统
作者: Guoxing Yu, Jingwen Dai
链接:https://arxiv.org/abs/1908.01450
【7】 Inference of visual field test performance from OCT volumes using deep learning
利用深度学习从OCT体积推断视野测试性能
作者: Stefan Maetschke, Rahil Garnav
链接:https://arxiv.org/abs/1908.01428
【8】 Image-Guided Depth Sampling and Reconstruction
图像制导深度采样与重建
作者: Adam Wolff, Guy Gilboa
链接:https://arxiv.org/abs/1908.01379
【9】 SF-Net: Structured Feature Network for Continuous Sign Language Recognition
SF-NET:用于连续手语识别的结构化特征网络
作者: Zhaoyang Yang, Yu-Wing Tai
链接:https://arxiv.org/abs/1908.01341
【10】 Theme Aware Aesthetic Distribution Prediction with Full Resolution Photos
全分辨率照片主题意识审美分布预测
作者: Gengyun Jia, Ran He
链接:https://arxiv.org/abs/1908.01308
【11】 To Learn or Not to Learn: Visual Localization from Essential Matrices
学习还是不学习:基本矩阵的视觉定位
作者: Qunjie Zhou, Laura Leal-Taixe
链接:https://arxiv.org/abs/1908.01293
【12】 Softmax Dissection: Towards Understanding Intra- and Inter-clas Objective for Embedding Learning
Softmax剖析:走向理解嵌入学习的班内和班际目标
作者: Lanqing He, Shengjin Wang
链接:https://arxiv.org/abs/1908.01281
【13】 Robust Subspace Discovery by Block-diagonal Adaptive Locality-constrained Representation
基于块对角自适应局部性约束表示的稳健子空间发现
作者: Zhao Zhang, Meng Wang
备注:accepted by ACM Multimedia 2019
链接:https://arxiv.org/abs/1908.01266
【14】 Attentive Normalization
注意归一化
作者: Xilai Li, Tianfu Wu
链接:https://arxiv.org/abs/1908.01259
【15】 Learning Guided Convolutional Network for Depth Completion
用于深度完成的学习引导卷积网络
作者: Jie Tang, Ping Tan
链接:https://arxiv.org/abs/1908.01238
【16】 Smooth Grad-CAM++: An Enhanced Inference Level Visualization Technique for Deep Convolutional Neural Network Models
Smooth Grad-CAM+:一种增强的深层卷积神经网络模型推理级可视化技术
作者: Daniel Omeiza, Komminist Weldermariam
备注:Accepted in the Intelligent Systems Conference 2019
链接:https://arxiv.org/abs/1908.01224
【17】 Learning to Predict 3D Objects with an Interpolation-based Differentiable Renderer
学习使用基于插值的可区分渲染器预测3D对象
作者: Wenzheng Chen, Sanja Fidler
链接:https://arxiv.org/abs/1908.01210
【18】 Permutation-invariant Feature Restructuring for Correlation-aware Image Set-based Recognition
基于置换不变特征重构的相关感知图像集识别
作者: Xiaofeng Liu, B.V.K. Kumar
备注:Accepted to ICCV 2019
链接:https://arxiv.org/abs/1908.01174
【19】 Adaloss: Adaptive Loss Function for Landmark Localization
Adaloss:用于地标定位的自适应损失函数
作者: Brian Teixeira, Ankur Kapoor
链接:https://arxiv.org/abs/1908.01070
【20】 High Accuracy Tumor Diagnoses and Benchmarking of Hematoxylin and Eosin Stained Prostate Core Biopsy Images Generated by Explainable Deep Neural Networks
可解释的深层神经网络生成的苏木素和曙红染色前列腺核心活检图像的高精度肿瘤诊断和标杆
作者: Aman Rana, Pratik Shah
链接:https://arxiv.org/abs/1908.01593
【21】 Knowledge Isomorphism between Neural Networks
神经网络之间的知识同构
作者: Ruofan Liang, Quanshi Zhang
链接:https://arxiv.org/abs/1908.01581
【22】 Precise Estimation of Renal Vascular Dominant Regions Using Spatially Aware Fully Convolutional Networks, Tensor-Cut and Voronoi Diagrams
利用空间感知的完全卷积网络、张量切割图和Voronoi图精确估计肾血管优势区域
作者: Chenglong Wang, Kensaku Mori
链接:https://arxiv.org/abs/1908.01543
【23】 CameraNet: A Two-Stage Framework for Effective Camera ISP Learning
CameraNet:一个有效学习相机ISP的两阶段框架
作者: Zhetong Liang, Lei Zhang
链接:https://arxiv.org/abs/1908.01481
【24】 Restricted Linearized Augmented Lagrangian Method for Euler's Elastica Model
Euler弹性模型的约束线性化增广拉格朗日方法
作者: Yinghui Zhang, Hongwei Li
链接:https://arxiv.org/abs/1908.01429
【25】 Improving IT Support by Enhancing Incident Management Process with Multi-modal Analysis
通过使用多模态分析增强事件管理流程来改进IT支持
作者: Atri Mandal, Daivik Swarup
链接:https://arxiv.org/abs/1908.01351
【26】 MoGA: Searching Beyond MobileNetV3
MOGA:搜索超越MobileNetV3
作者: Xiangxiang Chu, Ruijun Xu
链接:https://arxiv.org/abs/1908.01314
【27】 Building Deep, Equivariant Capsule Networks
构建深层等变胶囊网络
作者: Sairaam Venkatraman, R. Raghunatha Sarma
链接:https://arxiv.org/abs/1908.01300
【28】 CRNet: Image Super-Resolution Using A Convolutional Sparse Coding Inspired Network
CRNet:使用卷积稀疏编码启发的网络实现图像超分辨率
作者: Menglei Zhang, Lei Yu
链接:https://arxiv.org/abs/1908.01166
【29】 Toward Understanding Catastrophic Forgetting in Continual Learning
走向理解持续学习中的灾难性遗忘
作者: Cuong V. Nguyen, Stefano Soatto
链接:https://arxiv.org/abs/1908.01091
【30】 Y-Net: A Hybrid Deep Learning Reconstruction Framework for Photoacoustic Imaging in vivo
Y-NET:一种用于光声成像的混合深度学习重建框架
作者: Hengrong Lan, Fei Gao
链接:https://arxiv.org/abs/1908.00975
翻译:腾讯翻译君